Search Results for author:
Found 507 papers, 249 papers with code
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small.
Random Erasing Data Augmentation
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
Ranked #4 on
Image Classification
on Fashion-MNIST
Operation-aware Neural Networks for User Response Prediction
Many deep models are proposed to automatically learn high-order feature interactions.
Joint Discriminative and Generative Learning for Person Re-identification
To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end.
Ranked #1 on
Person Re-Identification
on UAV-Human
Image-to-Image Translation
Unsupervised Domain Adaptation
+1
VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
This stage relaxes the full alignment between the training and testing domains, as it is agnostic to the target vehicle domain.
Ranked #1 on
Vehicle Re-Identification
on VehicleID
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image.
Segment and Track Anything
This report presents a framework called Segment And Track Anything (SAMTrack) that allows users to precisely and effectively segment and track any object in a video.
Network Pruning via Transformable Architecture Search
The maximum probability for the size in each distribution serves as the width and depth of the pruned network, whose parameters are learned by knowledge transfer, e. g., knowledge distillation, from the original networks.
Ranked #1 on
Network Pruning
on CIFAR-10
Searching for A Robust Neural Architecture in Four GPU Hours
To avoid traversing all the possibilities of the sub-graphs, we develop a differentiable sampler over the DAG.
Ranked #18 on
Neural Architecture Search
on CIFAR-10
One-Shot Neural Architecture Search via Self-Evaluated Template Network
In this paper, we propose a Self-Evaluated Template Network (SETN) to improve the quality of the architecture candidates for evaluation so that it is more likely to cover competitive candidates.
Ranked #18 on
Neural Architecture Search
on NAS-Bench-201, ImageNet-16-120
(Accuracy (Val) metric)
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
A variety of algorithms search architectures under different search space.
Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
We propose to automatically search for a CNN architecture that is specifically suitable for the reID task.
Ranked #9 on
Person Re-Identification
on CUHK03 detected
Collaborative Video Object Segmentation by Foreground-Background Integration
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation.
Ranked #8 on
Video Object Segmentation
on YouTube-VOS 2019
ActBERT: Learning Global-Local Video-Text Representations
In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data.
Ranked #8 on
Action Segmentation
on COIN
T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval
Moreover, a global alignment method is proposed to provide a global cross-modal measurement that is complementary to the local perspective.
TAP-Vid: A Benchmark for Tracking Any Point in a Video
Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move.
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence.
Ranked #1 on
Visual Tracking
on Kinetics
BootsTAP: Bootstrapped Training for Tracking-Any-Point
To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes.
Self-Correction for Human Parsing
To tackle the problem of learning with label noises, this work introduces a purification strategy, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models.
Ranked #2 on
Human Part Segmentation
on PASCAL-Part
Style Aggregated Network for Facial Landmark Detection
In this work, we propose a style-aggregated approach to deal with the large intrinsic variance of image styles for facial landmark detection.
Ranked #2 on
Facial Landmark Detection
on AFLW-Front
(Mean NME metric)
Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection
A typical approach is to (1) train a detector on the labeled images; (2) generate new training samples using this detector's prediction as pseudo labels of unlabeled images; (3) retrain the detector on the labeled samples and partial pseudo labeled samples.
Ranked #1 on
Facial Landmark Detection
on 300W (Full)
(using extra training data)
Supervision by Registration and Triangulation for Landmark Detection
End-to-end training is made possible by differentiable registration and 3D triangulation modules.
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video.
Ranked #1 on
Facial Landmark Detection
on 300-VW (C)
A Multi-Mode Modulator for Multi-Domain Few-Shot Classification
Most existing few-shot classification methods only consider generalization on one dataset (i. e., single-domain), failing to transfer across various seen and unseen domains.
DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
It is one of the state-of-the-art SLAM systems in high-dynamic environments.
Robotics
A Simple Episodic Linear Probe Improves Visual Recognition in the Wild
In this paper, we propose an episodic linear probing (ELP) classifier to reflect the generalization of visual representations in an online manner.
Ranked #13 on
Fine-Grained Image Classification
on CUB-200-2011
Associating Objects with Transformers for Video Object Segmentation
The state-of-the-art methods learn to decode features with a single positive object and thus have to match and segment each target separately under multi-object scenarios, consuming multiple times computing resources.
Ranked #2 on
Video Object Segmentation
on DAVIS 2017 (test-dev)
(using extra training data)
Scalable Video Object Segmentation with Identification Mechanism
This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS).
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
To solve such a problem and further facilitate the learning of visual embeddings, this paper proposes a Decoupling Features in Hierarchical Propagation (DeAOT) approach.
Ranked #1 on
Semi-Supervised Video Object Segmentation
on VOT2020
Video Object Segmentation in Panoptic Wild Scenes
Considering the challenges in panoptic VOS, we propose a strong baseline method named panoptic object association with transformers (PAOT), which uses panoptic identification to associate objects with a pyramid architecture on multiple scales.
FinBERT: A Pretrained Language Model for Financial Communications
Contextual pretrained language models, such as BERT (Devlin et al., 2019), have made significant breakthrough in various NLP tasks by training on large scale of unlabeled text re-sources. Financial sector also accumulates large amount of financial communication text. However, there is no pretrained finance specific language models available.
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency.
Ranked #3 on
Person Re-Identification
on UAV-Human
University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i. e., drone-view target localization and drone navigation.
Ranked #6 on
Drone navigation
on University-1652
Multiple-environment Self-adaptive Network for Aerial-view Geo-localization
This task is mostly regarded as an image retrieval problem.
Unsupervised Scene Adaptation with Memory Regularization in vivo
We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data.
Ranked #1 on
Domain Adaptation
on SYNTHIA-to-Cityscapes Labels
Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation.
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks
Therefore, the network trained by our method has a larger model capacity to learn from the training data.
MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis
Lastly, we aggregate all the shaded instances to provide the necessary information for accurately generating multiple instances in stable diffusion (SD).
Ranked #1 on
Conditional Text-to-Image Synthesis
on COCO-MIG
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation.
Deep Hierarchical Semantic Segmentation
In this paper, we instead address hierarchical semantic segmentation (HSS), which aims at structured, pixel-wise description of visual observation in terms of a class hierarchy.
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
We verify the proposed method on a practical problem: person re-identification (re-ID).
Ranked #4 on
Person Re-Identification
on CUHK03
Fine-Grained Image Classification
Generative Adversarial Network
+2
Contrastive Adaptation Network for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain.
Ranked #7 on
Domain Adaptation
on Office-31
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
To achieve this goal, an exemplar memory is introduced to store features of the target domain and accommodate the three invariance properties.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
We consider the problem of unsupervised domain adaptation in semantic segmentation.
Ranked #8 on
Semantic Segmentation
on DADA-seg
Camera Style Adaptation for Person Re-identification
In this paper, we explicitly consider this challenge by introducing camera style (CamStyle) adaptation.
Ranked #71 on
Person Re-Identification
on DukeMTMC-reID
Dual-Path Convolutional Image-Text Embeddings with Instance Loss
In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space.
Ranked #1 on
Cross-Modal Retrieval
on CUHK-PEDES
A Discriminatively Learned CNN Embedding for Person Re-identification
We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i. e, verification and classification models.
Ranked #1 on
Person Re-Identification
on Market-1501+500k
Parameter-Efficient Person Re-identification in the 3D Space
To our knowledge, we are among the first attempts to conduct person re-identification in the 3D space.
GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature, class).
Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class.
Pedestrian Alignment Network for Large-scale Person Re-identification
This task aims to search a query person in a large image pool.
Ranked #1 on
Person Re-Identification
on CUHK03 (detected)
Unsupervised Person Re-identification: Clustering and Fine-tuning
Progressively, pedestrian clustering and the CNN model are improved simultaneously until algorithm convergence.
Ranked #12 on
Unsupervised Person Re-Identification
on DukeMTMC-reID
DeFlow: Decoder of Scene Flow Network in Autonomous Driving
Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving.
Ranked #1 on
Scene Flow Estimation
on Argoverse 2
Macro-Micro Adversarial Network for Human Parsing
To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN).
Ranked #12 on
Semantic Segmentation
on LIP val
Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation
Audio-driven talking-head synthesis is a popular research topic for virtual human-related applications.
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video Attribute Association mechanism, which leverages the Video-to-Text knowledge to generate textual auxiliary attributes for complementing video recognition.
Ranked #1 on
Zero-Shot Action Recognition
on ActivityNet
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
If the initial image is not well initialized, the following processes can hardly refine the image to a satisfactory quality.
Ranked #6 on
Text-to-Image Generation
on CUB
(Inception score metric)
One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation
In this paper, we propose Progressive Volume Distillation (PVD), a systematic distillation method that allows any-to-any conversions between different architectures, including MLP, sparse or low-rank tensors, hashtables and their compositions.
Ranked #1 on
Novel View Synthesis
on NeRF
(Average PSNR metric)
PVD-AL: Progressive Volume Distillation with Active Learning for Efficient Conversion Between Different NeRF Architectures
To address this limitation and maximize the potential of each architecture, we propose Progressive Volume Distillation with Active Learning (PVD-AL), a systematic distillation method that enables any-to-any conversions between different architectures.
PointGPT: Auto-regressively Generative Pre-training from Point Clouds
Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks.
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
To capture the dynamics in point cloud videos, point tracking is usually employed.
Ranked #4 on
3D Action Recognition
on NTU RGB+D
Perception Test: A Diagnostic Benchmark for Multimodal Models
We propose a novel multimodal benchmark – the Perception Test – that aims to extensively evaluate perception and reasoning skills of multimodal models.
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e. g. Flamingo, SeViLA, or GPT-4).
Self-produced Guidance for Weakly-supervised Object Localization
A stagewise approach is proposed to incorporate high confident object regions to learn the SPG masks.
Ranked #1 on
Weakly-Supervised Object Localization
on ILSVRC 2015
GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
In this work, we propose a model that can learn object transfiguration from two unpaired sets of images: one set containing images that "have" that kind of object, and the other set being the opposite, with the mild constraint that the objects be located approximately at the same place.
PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
We apply PointRNN, PointGRU and PointLSTM to moving point cloud prediction, which aims to predict the future trajectories of points in a set given their history movements.
LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updating
Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which has the advantages of lightweight storage and continuous querying.
Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection
Current methods for open-vocabulary object detection (OVOD) rely on a pre-trained vision-language model (VLM) to acquire the recognition ability.
D$^2$LV: A Data-Driven and Local-Verification Approach for Image Copy Detection
In this paper, a data-driven and local-verification (D$^2$LV) approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21.
Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer
Nowadays, deep learning techniques are widely used for lane detection, but application in low-light conditions remains a challenge until this day.
Generalizing A Person Retrieval Model Hetero- and Homogeneously
Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras.
Pyramid Diffusion Models For Low-light Image Enhancement
Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement.
Ranked #6 on
Low-Light Image Enhancement
on LOL
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion.
Gated Channel Transformation for Visual Recognition
This lightweight layer incorporates a simple l2 normalization, enabling our transformation unit applicable to operator-level without much increase of additional parameters.
Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark
In contrast, our large-scale VIdeo Panoptic Segmentation in the Wild (VIPSeg) dataset provides 3, 536 videos and 84, 750 frames with pixel-level panoptic annotations, covering a wide range of real-world scenarios and categories.
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
In this paper, to reduce the number of redundant video tokens, we design a multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones.
Ranked #11 on
Video Retrieval
on MSVD
(using extra training data)
What You Say and How You Say It Matters: Predicting Stock Volatility Using Verbal and Vocal Cues
Prior research has shown that textual information in a firm{'}s financial statement can be used to predict its stock{'}s risk level.
Visual Abductive Reasoning
In this paper, we propose a new task and dataset, Visual Abductive Reasoning (VAR), for examining abductive reasoning ability of machine intelligence in everyday visual situations.
SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
In this way, the possibilities embedded in the produced similarity maps can be adapted to guide the process of segmenting objects.
Ranked #89 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
In particular, we propose a transposed weight sharing scheme, which not only improves performance on image captioning, but also makes the model more suitable for the novel concept learning task.
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions.
Domain Consensus Clustering for Universal Domain Adaptation
To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones.
Ranked #4 on
Partial Domain Adaptation
on Office-31
DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training
This decoder is both data-efficient and computation-efficient: 1) it only requires the text data for training, easing the burden on the collection of paired data.
Bag of Tricks and A Strong baseline for Image Copy Detection
In this paper, a bag of tricks and a strong baseline are proposed for image copy detection.
Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains
Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.
Human101: Training 100+FPS Human Gaussians in 100s from 1 View
In this paper, we introduce Human101, a novel framework adept at producing high-fidelity dynamic 3D human reconstructions from 1-view videos by training 3D Gaussians in 100 seconds and rendering in 100+ FPS.
Content-Consistent Matching for Domain Adaptive Semantic Segmentation
The target of CCM is to acquire those synthetic images that share similar distribution with the real ones in the target domain, so that the domain gap can be naturally alleviated by employing the content-consistent synthetic images for training.
Ranked #12 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
Connecting Language and Vision for Natural Language-Based Vehicle Retrieval
In this paper, we apply one new modality, i. e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario.
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis
To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints.
Few-Example Object Detection with Model Communication
Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.
Ranked #1 on
Weakly Supervised Object Detection
on MS COCO
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
The conventional solution to this task is to minimize the discrepancy between source and target to enable effective knowledge transfer.
Ranked #25 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
Reconstructing 3D clothed human avatars from single images is a challenging task, especially when encountering complex poses and loose clothing.
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
Then, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension.
Ranked #3 on
3D Action Recognition
on NTU RGB+D
Lana: A Language-Capable Navigator for Instruction Following and Generation
Recently, visual-language navigation (VLN) -- entailing robot agents to follow navigation instructions -- has shown great advance.
Very Long Natural Scenery Image Prediction by Outpainting
The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input.
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
In an attempt to fill this gap, we propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts.
Ranked #1 on
Semantic Segmentation
on SYNTHIA-to-Cityscapes
Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph.
Ranked #1 on
Image Retrieval
on Oxford5k
Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks
We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles.
Computational Physics Applied Physics Optics
Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
To address the challenging task of instance-aware human part parsing, a new bottom-up regime is proposed to learn category-level human semantic segmentation as well as multi-person pose estimation in a joint and end-to-end manner.
SF-Net: Single-Frame Supervision for Temporal Action Localization
To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the temporal window of an action.
Ranked #5 on
Weakly Supervised Action Localization
on BEOID
Few-Shot Segmentation via Cycle-Consistent Transformer
Directly performing cross-attention may aggregate these features from support to query and bias the query features.
Ranked #52 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
We aim at the problem named One-Shot Unsupervised Domain Adaptation.
domain classification
One-shot Unsupervised Domain Adaptation
+2
Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization
Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas.
Ranked #3 on
Drone navigation
on University-1652
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
However, Sora, along with other text-to-video diffusion models, is highly reliant on prompts, and there is no publicly available dataset that features a study of text-to-video prompts.
Dialog Intent Induction with Deep Multi-View Clustering
We introduce the dialog intent induction task and present a novel deep multi-view clustering approach to tackle the problem.
CapHuman: Capture Your Moments in Parallel Universes
Moreover, we introduce the 3D facial prior to equip our model with control over the human head in a flexible and 3D-consistent manner.
3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective
This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image.
Ranked #1 on
Single-View 3D Reconstruction
on CUB-200-2011
Dynamic Computational Time for Visual Attention
We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM).
Personalized Video Recommendation Using Rich Contents from Videos
In the existing video recommender systems, the models make the recommendations based on the user-video interactions and single specific content features.
Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
Existing goal-oriented dialogue datasets focus mainly on identifying slots and values.
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
With such merits, we transform CLIP into a scene text reader and introduce CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP.
Ranked #1 on
Scene Text Recognition
on WOST
(using extra training data)
InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning
We present a new financial domain large language model, InvestLM, tuned on LLaMA-65B (Touvron et al., 2023), using a carefully curated instruction dataset related to financial investment.
Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation
However, using a single kind of modeling structure is difficult to balance the learning of short-term and long-term temporal correlations, and may bias the network to one of them, leading to undesirable predictions like global location shift, temporal inconsistency, and insufficient local details.
Ranked #46 on
3D Human Pose Estimation
on 3DPW
Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference.
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
Moreover, on the seemingly implausible x16 interpolation task, our method outperforms existing methods by more than 1. 5 dB in terms of PSNR.
Convolutional Neural Networks with Recurrent Neural Filters
We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters.
Ranked #11 on
Sentiment Analysis
on SST-5 Fine-grained classification
Unified Transformer Tracker for Object Tracking
Although UniTrack \cite{wang2021different} demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on single object tracking.
Overcoming Language Variation in Sentiment Analysis with Social Attention
Variation in language is ubiquitous, particularly in newer forms of writing such as social media.
Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.
MS-DETR: Efficient DETR Training with Mixed Supervision
The traditional training procedure using one-to-one supervision in the original DETR lacks direct supervision for the object detection candidates.
BLASX: A High Performance Level-3 BLAS Library for Heterogeneous Multi-GPU Computing
Basic Linear Algebra Subprograms (BLAS) are a set of low level linear algebra kernels widely adopted by applications involved with the deep learning and scientific computing.
Distributed, Parallel, and Cluster Computing
Local-Global Context Aware Transformer for Language-Guided Video Segmentation
We explore the task of language-guided video segmentation (LVS).
Ranked #7 on
Referring Expression Segmentation
on A2D Sentences
Referring Expression Segmentation
Referring Video Object Segmentation
+5
Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i. e., target domain.
Query-efficient Meta Attack to Deep Neural Networks
Black-box attack methods aim to infer suitable attack patterns to targeted DNN models by only using output feedback of the models and the corresponding input queries.
Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data
In the experiments, the proposed method is applied to ResNet and UNet, and the adjusted networks are verified on three very diverse benchmark data sets (i. e., Houston2018 data, Berlin data, and MUUFL data).
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
We hope MultiHop-RAG will be a valuable resource for the community in developing effective RAG systems, thereby facilitating greater adoption of LLMs in practice.
OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments
In this work, we propose OpenGraph, the first open-vocabulary hierarchical graph representation designed for large-scale outdoor environments.
DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results.
Feature-Proxy Transformer for Few-Shot Segmentation
With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head.
DenseBox: Unifying Landmark Localization with End to End Object Detection
How can a single fully convolutional neural network (FCN) perform on object detection?
RFNet: Region-Aware Fusion Network for Incomplete Multi-Modal Brain Tumor Segmentation
In this work, we propose a Region-aware Fusion Network (RFNet) that is able to exploit different combinations of multi-modal data adaptively and effectively for tumor segmentation.
Ranked #69 on
Semantic Segmentation
on NYU Depth v2
Attract or Distract: Exploit the Margin of Open Set
In this paper, we exploit the semantic structure of open set data from two aspects: 1) Semantic Categorical Alignment, which aims to achieve good separability of target known classes by categorically aligning the centroid of target with the source.
DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models
Recent LLM-driven visual agents mainly focus on solving image-based tasks, which limits their ability to understand dynamic scenes, making it far from real-life applications like guiding students in laboratory experiments and identifying their mistakes.
Unsupervised Domain Adaptation with Feature Embeddings
Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected by task-specific heuristics.
Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks
In the low-bit quantization field, training Binary Neural Networks (BNNs) is the extreme solution to ease the deployment of deep models on resource-constrained devices, having the lowest storage cost and significantly cheaper bit-wise operations compared to 32-bit floating-point counterparts.
Adaptive Exploration for Unsupervised Person Re-Identification
However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods.
Inter-Image Communication for Weakly Supervised Localization
We learn a feature center for each category and realize the global feature consistency by forcing the object features to approach class-specific centers.
ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022
In this report, we present the ReLER@ZJU-Alibaba submission to the Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2022.
Ranked #3 on
Natural Language Queries
on Ego4D
JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery
Our method includes an encoder-decoder transformer architecture to fuse 2D and 3D representations for achieving 2D$\&$3D aligned results in a coarse-to-fine manner and a novel 3D joint contrastive learning approach for adding explicitly global supervision for the 3D feature space.
Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning
To systematically measure the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i. e., Charades-CG and ActivityNet-CG.
SEEG: Semantic Energized Co-Speech Gesture Generation
Talking gesture generation is a practical yet challenging task which aims to synthesize gestures in line with speech.
Ranked #6 on
Gesture Generation
on TED Gesture Dataset
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Given a single test sample, the VLM is forced to maximize the CLIP reward between the input and sampled results from the VLM output distribution.
CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation
However, existing methods exhibit two limitations: 1) they address video temporal features and audio-visual interactive features separately, disregarding the inherent spatial-temporal dependence of combined audio and video, and 2) they inadequately introduce audio constraints and object-level information during the decoding stage, resulting in segmentation outcomes that fail to comply with audio directives.
Faster Meta Update Strategy for Noise-Robust Deep Learning
It has been shown that deep neural networks are prone to overfitting on biased training data.
Removing Raindrops and Rain Streaks in One Go
First, we propose a complementary cascaded network architecture, namely CCN, to remove rain streaks and raindrops in a unified framework.
Vector-Decomposed Disentanglement for Domain-Invariant Object Detection
Secondly, domain-specific representations are introduced as the differences between the input and domain-invariant representations.
V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval
While model ensemble is common, we show that combining the vision models and vision-language models brings particular benefits from their complementarity and is a key factor to our superiority.
MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering
To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must.
Ranked #2 on
Video Question Answering
on AGQA 2.0 balanced
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them.
Collective Entity Disambiguation with Structured Gradient Tree Boosting
To the best of our knowledge, our work is the first one that employs the structured gradient tree boosting (SGTB) algorithm for collective entity disambiguation.
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation.
H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection
How to align the source and target domains is critical to the CDWSOD accuracy.
Ranked #1 on
Weakly Supervised Object Detection
on Clipart1k
Context-Aware Pretraining for Efficient Blind Image Decomposition
(2) The conventional paradigm usually focuses on mining the abnormal pattern of a superimposed image to separate the noise, which de facto conflicts with the primary image restoration task.
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives
Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems.
CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes
In this work, we describe our creation of a dataset of clinical action items annotated over MIMIC-III, the largest publicly available dataset of real clinical notes.
Automated Progressive Learning for Efficient Training of Vision Transformers
First, we develop a strong manual baseline for progressive learning of ViTs, by introducing momentum growth (MoGrow) to bridge the gap brought by model growth.
Tele-Knowledge Pre-training for Fault Analysis
In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge normally found in both machine log data and product documents.
DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion
We present DiverseMotion, a new approach for synthesizing high-quality human motions conditioned on textual descriptions while preserving motion diversity. Despite the recent significant process in text-based human motion generation, existing methods often prioritize fitting training motions at the expense of action diversity.
Ranked #3 on
Motion Synthesis
on HumanML3D
(using extra training data)
Universal-Prototype Enhancing for Few-Shot Object Detection
Thus, we develop a new framework of few-shot object detection with universal prototypes ({FSOD}^{up}) that owns the merit of feature generalization towards novel objects.
Ranked #23 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization
Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network.
Ranked #2 on
Drone navigation
on University-1652
Gloss-Free End-to-End Sign Language Translation
In this paper, we tackle the problem of sign language translation (SLT) without gloss annotations.
Clustering based Point Cloud Representation Learning for 3D Analysis
The mined patterns are, in turn, used to repaint the embedding space, so as to respect the underlying distribution of the entire training dataset and improve the robustness to the variations.
Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
For example, Transformer Networks do not have native support on many popular chips, and hence are difficult to deploy.
Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification
Second, we instantiate the loss function and provide a strong baseline for FGVC, where the performance of a naive backbone can be boosted and be comparable with recent methods.
Ranked #27 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Visual Recognition
Improving Person Re-identification by Attribute and Identity Learning
Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions.
Ranked #75 on
Person Re-Identification
on DukeMTMC-reID
In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
By contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual quality of training data and is not robust to object deformation.
A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection
Moreover, this paper further reveals a unique difficulty for solving the hard negative problem in ICD, i. e., there is a fundamental conflict between current metric learning and ICD.
Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
With asymptotic pruning, the information of the training set would be gradually concentrated in the remaining filters, so the subsequent training and pruning process would be stable.
Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes
Albeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks.
Ranked #43 on
3D Part Segmentation
on ShapeNet-Part
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting
The core issue in MTS forecasting is how to effectively model complex spatial-temporal patterns.
Ranked #1 on
Time Series Forecasting
on Weather (96)
3D Pose Estimation for Fine-Grained Object Categories
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories
Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information.
Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
Our target is to learn visual correspondence from unlabeled videos.
GIF: A General Graph Unlearning Strategy via Influence Function
Then, we recognize the crux to the inability of traditional influence function for graph unlearning, and devise Graph Influence Function (GIF), a model-agnostic unlearning method that can efficiently and accurately estimate parameter changes in response to a $\epsilon$-mass perturbation in deleted data.
Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
In MOTOR, we combine two kinds of basic medical knowledge, i. e., general and specific knowledge, in a complementary manner to boost the general pretraining process.
DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval
(2) Equipping the visual and text encoder with separated prompts failed to mitigate the visual-text modality gap.
LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
Consequently, it is essential to develop LiDAR perception methods that are both efficient and effective.
UTS submission to Google YouTube-8M Challenge 2017
In this paper, we present our solution to Google YouTube-8M Video Classification Challenge 2017.
Connective Cognition Network for Directional Visual Commonsense Reasoning
Inspired by this idea, towards VCR, we propose a connective cognition network (CCN) to dynamically reorganize the visual neuron connectivity that is contextualized by the meaning of questions and answers.
Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation
In this work, we propose a new online VIS paradigm named Instance As Identity (IAI), which models temporal information for both detection and tracking in an efficient way.
Feature-compatible Progressive Learning for Video Copy Detection
Video Copy Detection (VCD) has been developed to identify instances of unauthorized or duplicated video content.
Whitening-based Contrastive Learning of Sentence Embeddings
Consequently, using multiple positive samples with enhanced diversity further improves contrastive learning due to better alignment.
RMP: A Random Mask Pretrain Framework for Motion Prediction
As the pretraining technique is growing in popularity, little work has been done on pretrained learning-based motion prediction methods in autonomous driving.
Fast and Accurate Factual Inconsistency Detection Over Long Documents
We introduce SCALE (Source Chunking Approach for Large-scale inconsistency Evaluation), a task-agnostic model for detecting factual inconsistencies using a novel chunking strategy.
LSMI-Sinkhorn: Semi-supervised Mutual Information Estimation with Optimal Transport
To estimate the mutual information from data, a common practice is preparing a set of paired samples $\{(\mathbf{x}_i,\mathbf{y}_i)\}_{i=1}^n \stackrel{\mathrm{i. i. d.
Triggerless Backdoor Attack for NLP Tasks with Clean Labels
To deal with this issue, in this paper, we propose a new strategy to perform textual backdoor attacks which do not require an external trigger, and the poisoned samples are correctly labeled.
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation
Tracking any given object(s) spatially and temporally is a common purpose in Visual Object Tracking (VOT) and Video Object Segmentation (VOS).
Ranked #10 on
Visual Object Tracking
on LaSOT
Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration
In this paper, we propose a deep learning-based character stroke extraction method that takes semantic features and prior information of strokes into consideration.
Compositional Feature Augmentation for Unbiased Scene Graph Generation
Specifically, we first decompose each relation triplet feature into two components: intrinsic feature and extrinsic feature, which correspond to the intrinsic characteristics and extrinsic contexts of a relation triplet, respectively.
Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields
Different from existing methods that consider cross-view and along-epipolar information independently, EVE-NeRF conducts the view-epipolar feature aggregation in an entangled manner by injecting the scene-invariant appearance continuity and geometry consistency priors to the aggregation process.
Ranked #1 on
Generalizable Novel View Synthesis
on Shiny dataset
Adversarial Complementary Learning for Weakly Supervised Object Localization
With such an adversarial learning, the two parallel-classifiers are forced to leverage complementary object regions for classification and can finally generate integral object localization together.
Ranked #2 on
Weakly-Supervised Object Localization
on ILSVRC 2016
Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
This paper considers the task of thorax disease classification on chest X-ray images.
CNN-RNN: A Unified Framework for Multi-label Image Classification
While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels, which could correspond to different objects, scenes, actions and attributes in an image.
Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
Most of previous work on adversarial attack mainly focus on image models, while the vulnerability of video models is less explored.
VidFace: A Full-Transformer Solver for Video FaceHallucination with Unaligned Tiny Snapshots
In this paper, we investigate the task of hallucinating an authentic high-resolution (HR) human face from multiple low-resolution (LR) video snapshots.
Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning
Specifically, we propose to meta-train the model on datasets of large sample sizes and transfer the knowledge to small datasets.
TransHP: Image Classification with Hierarchical Prompting
This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task.
PTGB: Pre-Train Graph Neural Networks for Brain Network Analysis
The human brain is the central hub of the neurobiological system, controlling behavior and cognition in complex ways.
Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition
In real-world scenarios, collected and annotated data often exhibit the characteristics of multiple classes and long-tailed distribution.
